Neural Lander: Stable Drone Landing Control using Learned Dynamics

Precise near-ground trajectory control is difficult for multi-rotor drones, due to the complex aerodynamic effects caused by interactions between multi-rotor airflow and the environment. Conventional control methods often fail to properly account for these complex effects and fall short in accomplishing smooth landing. In this paper, we present a novel deep-learning-based robust nonlinear controller (Neural Lander) that improves control performance of a quadrotor during landing. Our approach combines a nominal dynamics model with a Deep Neural Network (DNN) that learns high-order interactions. We apply spectral normalization (SN) to constrain the Lipschitz constant of the DNN. Leveraging this Lipschitz property, we design a nonlinear feedback linearization controller using the learned model and prove system stability with disturbance rejection. To the best of our knowledge, this is the first DNN-based nonlinear feedback controller with stability guarantees that can utilize arbitrarily large neural nets. Experimental results demonstrate that the proposed controller significantly outperforms a Baseline Nonlinear Tracking Controller in both landing and cross-table trajectory tracking cases. We also empirically show that the DNN generalizes well to unseen data outside the training domain.

Episodic Learning with Control Lyapunov Functions for Uncertain Robotic Systems

Many modern nonlinear control methods aim to endow systems with guaranteed properties, such as stability or safety, and have been successfully applied to the domain of robotics. However, model uncertainty remains a persistent challenge, weakening theoretical guarantees and causing implementation failures on physical systems. This paper develops a machine learning framework centered around Control Lyapunov Functions (CLFs) to adapt to parametric uncertainty and unmodeled dynamics in general robotic systems. Our proposed method proceeds by iteratively updating estimates of Lyapunov function derivatives and improving controllers, ultimately yielding a stabilizing quadratic program model-based controller. We validate our approach on a planar Segway simulation, demonstrating substantial performance improvements by iteratively refining on a base model-free controller.

NAOMI: Non-Autoregressive Multiresolution Sequence Imputation

Missing value imputation is a fundamental problem in modeling spatiotemporal sequences, from motion tracking to the dynamics of physical systems. In this paper, we take a non-autoregressive approach and propose a novel deep generative model: Non-AutOregressive Multiresolution Imputation (NAOMI) for imputing long-range spatiotemporal sequences given arbitrary missing patterns. In particular, NAOMI exploits the multiresolution structure of spatiotemporal data to interpolate recursively from coarse to fine-grained resolutions. We further enhance our model with adversarial training using an imitation learning objective. When trained on billiards and basketball trajectories, NAOMI demonstrates significant improvement in imputation accuracy (reducing average prediction error by 60% compared to autoregressive counterparts) and generalization capability for long range trajectories in systems of both deterministic and stochastic dynamics.

Optimizing Photonic Nanostructures via Multi-fidelity Gaussian Processes

We apply numerical methods in combination with finite-difference-time-domain (FDTD) simulations to optimize transmission properties of plasmonic mirror color filters using a multi-objective figure of merit over a five-dimensional parameter space by utilizing novel multi-fidelity Gaussian processes approach. We compare these results with conventional derivative-free global search algorithms, such as (single-fidelity) Gaussian Processes optimization scheme, and Particle Swarm Optimization---a commonly used method in nanophotonics community, which is implemented in Lumerical commercial photonics software. We demonstrate the performance of various numerical optimization approaches on several pre-collected real-world datasets and show that by properly trading off expensive information sources with cheap simulations, one can more effectively optimize the transmission properties with a fixed budget.

A General Method for Amortizing Variational Filtering

We introduce the variational filtering EM algorithm, a simple, general-purpose method for performing variational inference in dynamical latent variable models using information from only past and present variables, i.e. filtering. The algorithm is derived from the variational objective in the filtering setting and consists of an optimization procedure at each time step. By performing each inference optimization procedure with an iterative amortized inference model, we obtain a computationally efficient implementation of the algorithm, which we call amortized variational filtering. We present experiments demonstrating that this general-purpose method improves performance across several deep dynamical latent variable models.

A General Framework for Multi-fidelity Bayesian Optimization with Gaussian Processes

How can we efficiently gather information to optimize an unknown function, when presented with multiple, mutually dependent information sources with different costs? For example, when optimizing a robotic system, intelligently trading off computer simulations and real robot testings can lead to significant savings. Existing methods, such as multi-fidelity GP-UCB or Entropy Search-based approaches, either make simplistic assumptions on the interaction among different fidelities or use simple heuristics that lack theoretical guarantees. In this paper, we study multi-fidelity Bayesian optimization with complex structural dependencies among multiple outputs, and propose MF-MI-Greedy, a principled algorithmic framework for addressing this problem. In particular, we model different fidelities using additive Gaussian processes based on shared latent structures with the target function. Then we use cost-sensitive mutual information gain for efficient Bayesian global optimization. We propose a simple notion of regret which incorporates the cost of different fidelities, and prove that MF-MI-Greedy achieves low regret. We demonstrate the strong empirical performance of our algorithm on both synthetic and real-world datasets.

Teaching Multiple Concepts to a Forgetful Learner

How can we help a forgetful learner learn multiple concepts within a limited time frame? For long-term learning, it is crucial to devise teaching strategies that leverage the underlying forgetting mechanisms of the learner. In this paper, we cast the problem of adaptively teaching a forgetful learner as a novel discrete optimization problem, where we seek to optimize a natural objective function that characterizes the learner's expected performance throughout the teaching session. We then propose a simple greedy teaching strategy and derive strong performance guarantees based on two intuitive data-dependent properties, which capture the degree of diminishing returns of teaching each concept. We show that, given some assumptions about the learner's memory model, one can efficiently compute the performance bounds. Furthermore, we identify parameter settings of the memory model where the greedy strategy is guaranteed to achieve high performance. We demonstrate the effectiveness of our algorithm using extensive simulations along with user studies in two concrete applications, namely (i) an educational app for online vocabulary teaching and (ii) an app for teaching novices how to recognize animal species from images.

Learning to Search via Retrospective Imitation

We study the problem of learning a good search policy from demonstrations for combinatorial search spaces. We propose retrospective imitation learning, which, after initial training by an expert, improves itself by learning from its own retrospective solutions. That is, when the policy eventually reaches a feasible solution in a search tree after making mistakes and backtracks, it retrospectively constructs an improved search trace to the solution by removing backtracks, which is then used to further train the policy. A key feature of our approach is that it can iteratively scale up, or transfer, to larger problem sizes than the initial expert demonstrations, thus dramatically expanding its applicability beyond that of conventional imitation learning. We showcase the effectiveness of our approach on two tasks: synthetic maze solving, and integer program based risk-aware path planning.

PhaseLink: A Deep Learning Approach to Seismic Phase Association

Seismic phase association is a fundamental task in seismology that pertains to linking together phase detections on different sensors that originate from a common earthquake. It is widely employed to detect earthquakes on permanent and temporary seismic networks, and underlies most seismicity catalogs produced around the world. This task can be challenging because the number of sources is unknown, events frequently overlap in time, or can occur simultaneously in different parts of a network. We present PhaseLink, a framework based on recent advances in deep learning for grid-free earthquake phase association. Our approach learns to link phases together that share a common origin, and is trained entirely on tens of millions of synthetic sequences of P- and S-wave arrival times generated using a simple 1D velocity model. Our approach is simple to implement for any tectonic regime, suitable for real-time processing, and can naturally incorporate errors in arrival time picks. Rather than tuning a set of ad hoc hyperparameters to improve performance, PhaseLink can be improved by simply adding examples of problematic cases to the training dataset. We demonstrate the state-of-the-art performance of PhaseLink on a challenging recent sequence from southern California, and synthesized sequences from Japan designed to test the point at which the method fails. These tests show that PhaseLink can precisely associate P- and S-picks to events that are separated by ~12 seconds in origin time. This approach is expected to improve the resolution of seismicity catalogs, add stability to real-time seismic monitoring, and streamline automated processing of large seismic datasets.